Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 4125
    Prev
    Next
    INDEX
    Explanations

    identifiers and symbols commonly used in programming and mathematical equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PEL
    -0.66
    Osob
    -0.66
     defaultdict
    -0.65
    IsPostBack
    -0.64
    soort
    -0.64
     dima
    -0.64
    Mane
    -0.63
    addGap
    -0.62
    listdir
    -0.61
    Parameteri
    -0.61
    POSITIVE LOGITS
    getX
    1.42
     X
    1.41
     getX
    1.40
     Xanth
    1.36
     Xavier
    1.35
     xanth
    1.34
     Xander
    1.34
     Xs
    1.28
    setX
    1.25
     maxX
    1.24
    Activations Density 0.716%

    No Known Activations